A note on maximum likelihood estimation of the initial number of susceptibles in the general stochastic epidemic model

The initial number of susceptible individuals in a population is usually assumed to be known and statistical inference for some of the quantities of interest, such as the basic reproductive number R(0), is straightforward. However, in any epidemic, there may exist a number of individuals who may not be involved in the transmission of the disease. In this note we show how maximum likelihood estimators can be derived for the parameters of interest. The proposed methodology is then applied to the Abakaliki smallpox data in Nigeria. (C) 2009 Elsevier B.V. All rights reserved.